© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 38821
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¤ļ个
    -0.31
    åĿĩ
    -0.29
    ä¸įä¸Ģæł·
    -0.27
    ç®ĹäºĨ
    -0.26
    ä¸įæĥ³
    -0.26
    便
    -0.26
    nett
    -0.26
    计ç®Ĺ
    -0.26
    举
    -0.26
    EGIN
    -0.26
    POSITIVE LOGITS
     flip
    0.30
    èĭ«
    0.28
     Flip
    0.28
    æ¼Ĥæµģ
    0.27
    owers
    0.27
    apia
    0.25
    çļ¿
    0.25
    _flip
    0.25
    owing
    0.25
     Khánh
    0.24
    Activations Density 50.518%

    No Known Activations

    This feature has no known activations.